Skip to content
Linkbricks Horizon-AI
Technology

HORIZON-AI

LLM SERVER

Linkbricks Horizon-AI Server: a high-performance AI model deployment platform. The Linkbricks Horizon-AI Server is a robust, scalable solution for deploying and managing AI models in production environments. Designed to meet the diverse needs of modern AI applications, it supports a wide range of hardware configurations, ecosystems, and deployment options, delivering unparalleled performance and flexibility.

0208Explore
  • 01Quantized Model Support (4, 8, 16, 32)Support for multiple quantization levels maximizes model performance and efficiency across different hardware environments.
  • 02Various NPU/GPU SupportFull compatibility with a wide range of NPUs (Neural Processing Units) and GPUs enables smooth deployment across diverse hardware platforms.
  • 03Multi-GPU/NPU Processing SupportMulti-GPU/NPU configurations handle large-scale AI workloads, delivering faster processing speeds and improved scalability.
  • 04Huggingface, Ollama Ecosystem SupportSeamless integration with Hugging Face and Ollama makes it easy to connect with popular AI tools and frameworks.
  • 05Tool Calling Prompt SupportTool calling prompts allow external tools to be integrated within workflows, simplifying complex tasks.
  • 06Rest-API SupportA complete REST API enables smooth communication and automation with external systems.
  • 07Flexible Deployment: Cloud or On-PremiseBoth cloud-based and on-premise deployment are supported, meeting scalability, security, and compliance requirements.
08

Configuration & Integration

  • Function Call with Rest-API
  • Support Local Inference
  • Horizon-AI Server + Open WebUI

Technology Gallery

4 images

Technology

Back to — Technology